AI Coding Agents

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 115% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 212

Jun 15, 2026cs.CL

Can LLM Coding Agents Reason About Time Series?

Large language models (LLMs) are increasingly being used for automated decision-making systems in finance, healthcare, or environmental monitoring. Time series data are ubiquitous in these fields, yet hard to process automatically. Can time series be analyzed by LLM agents? We examine three approaches: providing the agent with raw numerical data, using the LLM as a coding agent, or a combination of both. In the coding agent setup, the model iteratively queries the data using Python code. Using two time series understanding benchmarks, we show that agents with code access can outperform models processing raw data by up to 10%. However, even the best performing agent still answers about 22-34% of the questions incorrectly. To get insights into models' strategies and reasoning gaps, we analyze the model outputs with a strong LLM judge. Our analysis reveals that coding agents can select appropriate statistical tests, but often miss important nuances. Meanwhile, models with access to raw data can reach the right conclusions using back-of-the-envelope calculations.

Filip Rechtorík, Ondřej Dušek, Zdeněk Kasner

Institute of Formal and Applied Linguistics Faculty of Mathematics and Physics, Charles University

Time Series Reasoning Time Series QA AI Coding Agents LLM Agent Evaluation

Jun 15, 2026cs.RO

RHO: Your Coding Agent is Secretly a Roboticist

Code-as-Policies (CaP) has shown that large language models (LLMs) can write code to solve robotics tasks by composing perception, planning, and control primitives. Recent CaP systems, however, rely on multi-turn code-generation loops at test time, which is often infeasible for real-time robot control. We introduce Robotics Harness Optimization (RHO), a novel paradigm in which tool-enabled coding agents, at training time, propose and search for interpretable, neurosymbolic multi-file policy repositories (Repositories-as-Policies) that compose these primitives rather than a single prompt, function, or file. RHO searches with reflective feedback from environment reward and execution rather than teleoperation demonstrations. It generalizes to perturbed pick-and-place settings like LIBERO-PRO, where OpenVLA scores 0.0% and

π_{0.5}

averages 12.83%. Using the same low-level primitives, RHO reaches a 45.0% success rate, 2.5x higher than the strongest multi-turn agentic system, and 3.5x higher than

π_{0.5}

. On Robosuite, RHO sets a new state-of-the-art of 70.0%, exceeding the prior multi-turn record of 68.29% using single-turn execution with no corrective LLM code edits at deployment. When an LLM is used in the control loop, as on RAI's O3DE benchmark, RHO optimizes the deployed agent's multi-file harness of prompts, tools, and control code, improving held-out success from 23.5% to 44.3% with 20% less wall-clock time and 27% fewer tool calls.

Karim Elmaaroufi, Justin Svegliato, Sarunas Kalade +3

University of California, Berkeley · Embodied Science · AMD

Robot Policy Learning AI Coding Agents Large Language Model-Based Robot Planning Program Synthesis Agent Harness Optimization AI Control+2

Jun 14, 2026cs.SE

Software Delegation Contracts: Measuring Reviewability in AI Coding-Agent Work

AI coding agents increasingly accept assigned software tasks, modify repositories under bounded authority, and return work packages for review. Prior work proposed the software delegation contract, covering the task, authority, returned work package, and acceptance context, as the unit of analysis for delegated coding work, but did not measure its effects. This paper reports a controlled pilot study of explicit delegation contracts for coding agents. We built a dependency-free TypeScript API task environment with seeded defects and documentation gaps, authored ten tasks across five families, and ran 64 agent executions across two model tiers under three conditions: a realistic issue-style prompt, an explicit delegation contract, and a contract with a required evidence bundle. Each run was scored with hidden acceptance tests, mutation checks, and scope analysis, then reviewed by three independent condition-blinded model-based reviewers using a fixed rubric, for 192 reviews. Explicit contracts did not improve objective task outcomes: all 64 runs passed hidden acceptance checks, with zero scope violations. They did improve reviewability. Evidence sufficiency improved in 22 of 30 paired comparisons and worsened in none (+0.83 on a 5-point scale, p < 0.0001, Cliff's delta = 0.66); reviewer ambiguity decreased (p = 0.035); changed-file lists, known-limitations sections, residual-risk sections, and reviewer checklists appeared mostly or only when demanded by the contract. Contracts cost +13% agent tokens and +38% wall-clock time, with larger effects for the weaker model tier. On these small tasks, delegation contracts bought reviewability rather than correctness.

Vincent Schmalbach

Independent Researcher

AI Coding Agents Code Generation Evaluation

Jun 13, 2026cs.SE

ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures

Software engineering and deployment are increasingly delegated to AI coding agents. The scale of their adoption is surfacing rare, but highly destructive, failure modes. In this paper, we study these failure modes as stemming from three distinct mechanisms: underspecification, where default model behavior is unsafe; capability errors, where the safe action is available but the model does not adhere to it due to bias or capability limitations; and agent harness errors, where the model fails to execute the safe action through the harness. We assess these across 8 different evaluations, each inspired by real-life deployment failures, totaling 20 coding environments and 59 synthetic transcript templates. These evaluations act as controlled stress tests for isolating our failure mechanisms. Based on this evaluation, we propose ClayBuddy, a harness modification that molds to user preferences and can be modified by the model in-session, to mitigate these errors. By adding tools for the agent to edit its own context, an extended system prompt, a customizable command classifier, and deterministic guardrails, we show that ClayBuddy is safer across a statistically significant number of samples. Thus, we suggest concrete mitigations for current coding agents and a design philosophy for future agent harness features.

Kenneth Ge, Andre Assis

Anthropic Fellows Program · Constellation

Agent Failure Analysis AI Coding Agents AI Agent Safety AI Agent Safety Benchmarks Agentic AI

Jun 13, 2026cs.AI

CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?

Advanced agents are increasingly demonstrating the potential to operate as autonomous engineers, creating a growing demand for evaluation benchmarks that capture the complexity of real-world development. Such environments typically involve both complex code and large-scale data (i.e., file system). However, existing benchmarks usually evaluate code-centric or data-centric capabilities in isolation, leaving a clear gap with real development scenarios. In this paper, we bridge this gap by introducing CODA-BENCH, the first benchmark to jointly evaluate code and data intelligence in a data-intensive environment. We construct a data-intensive Linux sandbox based on the Kaggle ecosystem (containing hundreds of datasets), where agents must actively explore complex file hierarchies to identify relevant resources and generate code for data-driven analytical tasks. CODA-BENCH comprises 1,009 tasks spanning 31 communities, with each task environment containing an average of 980 files, simulating realistic data scale and noise. Evaluations of advanced agents reveal that even top-performing systems struggle to effectively integrate data discovery with code execution, achieving a success rate of only 61.1%. These results highlight a substantial gap in current agentic capabilities for data-intensive tasks and point to promising directions for future research.

Yuxin Zhang, Ju Fan, Meihao Fan +2

Renmin University of China

AI Coding Agents Software Engineering Benchmarks Code Generation AI Agent Benchmarks Code Generation Benchmarks

Jun 11, 2026cs.SE

Mining Architectural Quality Under Agentic AI Adoption: A Causal Study of Java Repositories

AI coding tools are now used by a majority of developers, and agentic use of these tools has popularized the practice colloquially called "vibe coding". Yet causal evidence on their effect on software architecture is scarce. Prior causal work has measured code-level outcomes (complexity, static analysis warnings); whether such degradation propagates to architecture-level outcomes remains unknown. We mine 151 open-source Java repositories, 74 with detectable agentic AI adoption (identified via configuration files and Co-Authored-By commit trailers) and 77 propensity-matched controls, across a 13-month per-repository window yielding 1,811 monthly Arcan snapshots. We estimate the causal effect of adoption on architectural smell density (ASD) with a staggered difference-in-differences design and the Borusyak imputation estimator, applying a causal design recently used for code-level metrics to the architecture level. Total smell counts are essentially unchanged (+1.1%, p = 0.82) while lines of code grow +12.8% (p = 0.003); the resulting 6.7% ASD decline (p = 0.004) is therefore a denominator effect rather than an architectural improvement. Per-type estimates and robustness checks (wild cluster bootstrap, Lee bounds, stale-observation sensitivity) corroborate the pattern; pre-trends are flat (Wald p = 0.90), consistent with parallel trends. Density-normalized outcomes can mislead when treatment affects system size: raw counts and explicit decomposition are required for causal mining studies of AI tool adoption. The complete replication package, including the curated 151-repository monthly panel, is publicly available.

Oliver Aleksander Larsen, Mahyar T. Moghaddam

SDU Software Engineering, University of Southern Denmark, Odense, Denmark

AI Coding Agents Automated Software Engineering

Jun 10, 2026cs.LG

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

The software engineering capabilities of general-purpose agent harnesses remain underexplored, and existing benchmarks offer limited support for comparing these harnesses under consistent conditions. To address this gap, we introduce Claw-SWE-Bench, a unified benchmark that enables researchers to systematically assess the capabilities and efficiency of general-purpose harnesses on software engineering tasks. The benchmark contains 350 real-world GitHub issue-resolution instances across eight programming languages and 43 repositories and provides a shared adapter protocol to align task inputs, outputs, and execution environments across harnesses. Experiments show that general-purpose harnesses can effectively resolve real-world software issues and that their success rates and resource consumption vary substantially even when the underlying model is held fixed. To lower evaluation costs and support faster debugging and iteration, we also provide Claw-SWE-Bench Lite, an 80-instance subset designed to preserve the key evaluation properties of the full benchmark. We hope this benchmark will help researchers better evaluate and understand the performance of general-purpose harnesses on software engineering tasks and guide the development of more capable and efficient harnesses. The data is available at https://github.com/opensquilla/claw-swe-bench and https://huggingface.co/datasets/TokenRhythm/Claw-SWE-Bench.

Mengyu Zheng, Kai Han, Boxun Li +13

TokenRhythm Technologies · Infinigence AI · Peking University +5

AI Coding Agents Software Engineering Benchmarks Agent Evaluation AI Agent Benchmarks

Jun 10, 2026cs.AI

PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents

AI coding agents often lose project-specific rationale across sessions and may repeat approaches that previously failed. The bottleneck is often not model capability but missing coding agent memory: a durable record of what was decided, tried, and ruled out. We present projectmem, an open-source, local-first memory and judgment layer for AI coding agents, which records development as an append-only, plain-text log of typed events (issues, attempts, fixes, decisions, and notes) and deterministically projects it into compact summaries served through the Model Context Protocol (MCP). When invoked before an edit, a file-scoped advisory precheck returns recorded failures, open issues, and churn for the target file, a design point we call Memory-as-Governance. We evaluate feasibility through an author-run, six-month self-study on two machines, a controlled latency benchmark, and client-compatibility tests. The study contains 3,228 unique events from 27 projects; 56% are issue-lifecycle events, and 86 of 427 distinct issues closed by a recorded fix had at least one failed attempt before the first fix in event-log order. These histories are candidates for later warnings, not evidence that warnings prevented failures. On a synthetic repository, the median analysis time for a 1,500-event log decreased from 42.0 seconds to 79.3 milliseconds, while git subprocesses per check decreased from 1,500 to two and the tested warning output was preserved. The results establish the feasibility of persistent project memory for AI coding agents and motivate a controlled repeat-failure benchmark for measuring whether coding-agent memory prevents repeated failures. Source code is available at https://github.com/riponcm/projectmem.

Ripon Chandra Malo, Tong Qiu

University of Utah

AI Coding Agents LLM Agent Memory Agent Memory Management

Jun 10, 2026cs.SE

Exploration Structure in LLM Agents for Multi-File Change Localization

Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step. We postulate that this is a structural mismatch for changes that span several subsystems. We compare linear sequential exploration against non-linear, domain-scoped parallel agentic exploration. Using SWE Bench Pro as initial benchmark, we focus on ansible as an exemplar. We construct an approach for persistent-session evaluation of GitHub issues anchored at a single base commit. We compare our non-linear domain-agent file traversal system against a base LLM without direct repository access, a single agent Recursive Language Model (RLM) baseline with a persistent Python REPL and an external CLI baseline using Codex 5.5 High. Domain scoped parallel agent spawning with a small Haiku-class model achieves the highest micro F1 among Haiku class models by a large margin. Domain-agents is the second highest behind only the much larger Codex 5.5 High on our own expanded benchmark including over more recent PRs from 2025 and 2026. On the original, curated, 2020 SWE-bench Pro benchmark, a larger Sonnet plain LLM baseline attains higher micro F1 by predicting few files, leading to higher precision, but at significantly lower all gold recall. We also present three additional findings. First, documentation evolution is a latent dependency unresolved by any approach. Second, naive file system access can degrade localization driven by test-file over prediction. Lastly, forced multi-agent consultation does not measurably help and raises token cost substantially.

Akeela Darryl Fattha, Kia Ying Chua, Lingxiao Jiang +1

School of Computing and Information Systems Singapore Management University Singapore

Software Engineering Software Engineering Agents AI Coding Agents Multi-Agent LLMs

Jun 9, 2026cs.CL

AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable

The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may amplify the analytic flexibility through which researchers reach motivated conclusions. We argue these worries target two empirically separable layers: a design layer of methodological choices, and a verdict layer in which a decision rule maps estimates to a substantive claim. We test both by running 20 independent executions of Claude Code and Codex on a prominent immigration and social-policy against a many-analysts human baseline. At the design layer, Codex matches human methodological diversity and Claude Code produces nearly three times as many specifications; both agents' effect estimates remain broadly aligned with the human consensus, and no agent model exactly matches any human model. A prompt-induced anti-immigration researcher prior reorganizes each agent's methodological decisions but, unlike for biased human analysts in the same data, does not shift aggregate estimates or final verdicts; nor do agents reroute along the methodological axes humans use to bias their estimates. At the verdict layer, an explicit confirmatory prompt flips Claude Code's verdicts from 10% to 90% support while leaving its coefficient distribution essentially unchanged, operating through rule omission rather than rule softening. AI agents can rival or exceed human methodological diversity at the design layer while remaining vulnerable at the verdict layer. In our setting, the locus of AI bias is not estimation but interpretation.

Meysam Alizadeh, Fabrizio Gilardi, Mohsen Mosleh +1

University of Oxford · University of Zurich · Technical University of Munich

AI Agent Reliability AI Coding Agents LLM Agent Evaluation Computational Social Science Language Model Bias Evaluation

Jun 9, 2026cs.CL

AI Coding Agents Can Reproduce Social Science Findings

Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic evaluation across social sciences remains limited. Existing evaluation benchmarks are insufficient, either small or conflate agent performance with problems in the reproduction materials themselves, such as code that fails to execute correctly. Here we introduce SocSci-Repro-Bench, a benchmark of 221 tasks spanning four disciplines and 13 substantive domains, constructed from studies whose results are either fully reproducible with available materials or demonstrably non-reproducible due to missing data, allowing us to isolate agents' reproduction capacity. Evaluating two frontier coding agents, Claude Code and Codex, we find that both can reproduce a large share of social science findings, with Claude Code substantially outperforming Codex. These reproduction rates considerably exceed those previously reported for general-purpose LLM-based agents on comparable reproducibility benchmarks. Both agents also perform strongly on a reasoning task requiring identification of underlying research questions, and additional analyses suggest that results are not primarily driven by memorization. Providing the original paper PDF alongside replication materials modestly improves performance but introduces bias on tasks where reproduction is impossible. We also show that agents can be nudged toward confirmatory specification search through subtle prompt framing. Together, these findings suggest that at least some frontier coding agents can serve as reliable executors of computational workflows while underscoring the need for careful benchmarking and prompt design as AI systems assume larger roles in scientific production.

Meysam Alizadeh, Mohsen Mosleh, Fabrizio Gilardi +2

University of Oxford · University of Zurich · Carnegie Mellon University +1

AI Coding Agents AI Agent Benchmarks Computational Social Science Scientific Reproducibility

Jun 9, 2026cs.AI

AutoPDE: Reliable Agentic PDE Solving via Explicitly Represented Solver Strategies

Numerical solvers for partial differential equations (PDEs) are core computational tools in science and engineering. Building reliable PDE solvers requires not only executable code, but a numerical solver strategy, a set of decisions about discretization, stabilization, solver configuration, and resolution control, that matches the PDE structure. Recent LLM-based coding agents have begun to reduce the programming burden by generating and debugging solver implementations. However, they typically move directly from a PDE problem to solver code, leaving the solver strategy implicit in implementation details. Feedback from a failed solve is therefore routed back to code edits rather than to the underlying strategy, so numerical decisions remain hard to check before code is generated and hard to revise using numerical evidence when it fails. To address this limitation, we propose AutoPDE, a code agent that maintains the solver strategy as an explicitly represented object throughout the solving process: an independent, inspectable object that is built before any code is written and can be revised, using numerical evidence, whenever a solve fails. AutoPDE builds and maintains this object in three stages, all drawing from a library of reusable PDE-solving skills: PDE analysis identifies the equation type and algebraic structure; numerical method selection chooses a numerical method that matches the analysis result and commits to a discretization, stabilization, and linear solver accordingly; and adaptive tuning runs low-cost pilot solves to calibrate resolution and tolerances under the prescribed accuracy and runtime budget. We evaluate AutoPDE on the PDE Agent Bench, where experimental results show that AutoPDE achieves a pass rate of

54.5%

, improving over the strongest baseline by

14.2

percentage points.

Huanshuo Dong, Keyao Zhang, Hong Wang +6

University of Science and Technology of China · 2Zhejiang University · University of the Chinese Academy of Sciences +2

AI Coding Agents PDE Solving

Jun 8, 2026cs.SE

What makes a harness a harness: necessary and sufficient conditions for an agent harness

The term agent harness now circulates widely in software engineering with generative artificial intelligence. It names the layer that wraps a language model and turns it into a coding agent able to act on a repository. The usage is loose and polysemous. Sometimes the term denotes the whole product (Claude Code, Codex CLI); sometimes it denotes the evaluation scaffold that runs an agent against tasks (the SWE-bench harness); sometimes it gets conflated with an agent framework, an SDK, an IDE plugin, or an orchestrator. What is missing is a reference definition that works as an instrument, one that includes and excludes cases consistently. We build that definition through a conceptual analysis that combines works with persistent identifiers and primary grey-literature sources, such as official documentation, glossaries, and engineering reports. We reconstruct the genealogy of the term, from the horse's tack to the classic test harness, to the machine-learning evaluation harness, and finally to the agent harness. We then propose a constitutive definition that states the necessary and sufficient conditions for a system to be an agent harness, we operationalize it as an inclusion and exclusion test, and we draw the boundary of the concept against an agent framework, an agent SDK, an IDE plugin, an eval harness, and an orchestrator. We apply the definition to six real harnesses (Claude Code, Codex CLI, Aider, Cline, OpenHands, and SWE-agent) and to deliberate edge cases; the test includes and excludes consistently. We close with a research agenda organized by design tension axes. The contribution is an operational definition of agent harness, with a shared vocabulary, able to guide engineering practice and the scientific comparison of agentic systems.

Sanderson Oliveira de Macedo

Federal Institute of Goiás

Software Engineering Agents AI Coding Agents LLM Agent Harnesses

Jun 5, 2026cs.LG

Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories

LLM-based coding agents sometimes acknowledge a problem in their own reasoning and then proceed anyway. We call this pattern strained coherence: a safety-relevant failure mode in which an agent has information that should change its behavior, states that information, and still acts against it. The pattern overlaps with verbalized reward hacking, where an agent names a tension between a task proxy and the underlying goal yet optimizes the proxy anyway. We give an operational definition, build a Claude Sonnet 4.6 judge that reads full trajectories and flags spans where the pattern occurs, and evaluate it on 44 Terminal-bench-2 trajectories using a Qwen3.5-35B-A3B backbone. Flagged trajectories fail 94% of the time versus 46% for unflagged trajectories (47-point gap, Fisher's exact p = 0.003; 46 points after excluding three prompt-embedded examples, p = 0.006). At matched selectivity, the detector reaches 94% precision versus 88% for a lexical discourse-marker baseline; the 10-trajectory intersection of the two methods has a 100% failure rate (Clopper-Pearson 95% CI [69%, 100%]). We replicate on Gemma4-31B with 43 trajectories: the overall signal is directionally consistent but not significant (20-point gap, p = 0.31), with attenuation driven largely by 13 trajectories with zero think content, where the detector has no substrate to analyze. In the high-verbosity Gemma tertile, the gap is +30 points; in the mid- and high-verbosity Qwen tertiles, it is +40 points each. The first flag appears at a median of 83-84% of elapsed trajectory time across both models, and the binary flag survives paraphrases that soften explicit conflict markers (8/8 trajectories). Unlike univariate predictors, the detector emits interpretable span-level output -- quoted acknowledgment, quoted action, and typed conflict -- showing what the agent saw and ignored.

Marut Pandya, Kasey Zhang, Baiqing Lyu

AI Coding Agents AI Agent Monitoring LLM Agent Reliability

Jun 5, 2026cs.SE

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieval, code localization, and bug diagnosis. In this paper, we introduce SWE-Explore, a benchmark that isolates the evaluation of repository exploration, a critical capability of coding agents. Given a repository and an issue, SWE-Explore asks an explorer to return a ranked list of relevant code regions under a fixed line budget. SWE-Explore covers 848 issues across 10 programming languages and 203 open-source repositories. For each instance, we derive line-level ground truth from independent agent trajectories that successfully solved the same issue, distilling the specific code regions their solution paths actually consulted. We evaluate exploration along coverage, ranking, and context-efficiency dimensions, showing that these metrics strongly track downstream repair behavior. Across a broad set of retrieval methods, general coding agents, and specialized localizers, we find that agentic explorers form a clear tier above classical retrieval. While file-level localization is already strong for modern methods, line-level coverage and efficient ranking remain the key axes differentiating state-of-the-art explorers.

Shaoqiu Zhang, Yuhang Wang, Jialiang Liang +8

1Shanghai Jiao Tong University · 2Xinjiang University · 4Independent Researcher +2

AI Coding Agents Agentic Search Software Engineering Benchmarks Information Retrieval

Jun 5, 2026cs.SE

SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?

AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments. Yet current agent benchmarks largely evaluate short-form tasks, such as single pull requests, small tickets, or 5-10 minute exercises, limiting our ability to measure agents' capabilities in planning, long-context understanding, and memory use. We introduce SWE-Marathon, a benchmark of 20 long-horizon tasks spanning software engineering and adjacent technical domains. Each task consists of a unique executable environment, a human-written reference solution, and a multi-layer verification suite. Logged agent attempts average 27.2M total tokens, making SWE-Marathon substantially longer-horizon than existing SWE and command-line agent benchmarks. Current frontier coding agents solve fewer than 30% of tasks. Failures often arise from poor self-verification, self-reported infeasibility, and premature termination. We also observe reward-hacking behavior in 13.8% of rollouts, where agents attempt to exploit the environment or verifier to bypass the intended workflow. SWE-Marathon includes adversarial review of test suites and execution environments, as well as multi-layer checks designed to prevent shortcut solutions. We release SWE-Marathon, evaluation code, and agent trajectories at https://swe-marathon.org/.

Rishi Desai, Jesse Hu, Joan Cabezas +23

Abundant · Zenity · Harvard University +14

AI Coding Agents Software Engineering Benchmarks Long-Horizon Agent Evaluation Long-Horizon Agent Tasks

Jun 4, 2026cs.SE

Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement

Existing code-generation benchmarks score a single mapping from a complete prompt to a one-shot output. However, real web development is different. Users seldom write a full spec at the start; many requirements only become clear once they look at an intermediate result and react to it. We present Asuka-Bench, a benchmark that pairs underspecified user intent with multi-round refinement, grounded in browser-rendered behavior. Each task is resolved through a closed loop: a Code Agent generates a web project, a UI Agent executes test cases on the deployed site, and a User LLM turns evaluation outcomes into natural-language feedback for the next round. The benchmark comprises 50 web tasks with 784 evaluation criteria and 2402 expected outcomes. We benchmark 8 LLMs across 2 agent frameworks. The results separate models clearly: weighted Task Pass Rate varies by 38 percentage points and models also differ substantially in their ability to repair from feedback. Asuka-Bench is also far from saturated: even the strongest model completes only 52% of projects after three rounds.

Xin Wang, Liangtai Sun, Yaoming Zhu +8

University of Science and Technology of China · 2Independent researchers

Computer-Use Agent Benchmarks Language Model Generation Evaluation AI Coding Agents Code Generation AI Agent Benchmarks Code Generation Benchmarks

Jun 4, 2026cs.SE

Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation

Large language models and AI coding agents have reshaped software development, but the path to fully AI-native systems faces structural challenges. Chief among them is managing context windows without losing accuracy or efficiency. When developers inject full project documentation and code into a model's memory, the model loses mid-sequence information, token costs spiral, and architecture drifts. This paper presents MicroSkill Architecture: a modular design paradigm inspired by microservices, applied to knowledge encapsulation instead of service decomposition. Instead of feeding an agent the entire codebase, the architecture partitions knowledge into atomic, sharply scoped skill capsules, and a dynamic router selects only semantically relevant capsules for the task. We formally model context allocation as constrained optimization over semantic relevance subject to a token budget. An empirical case study an enterprise content management system with fifteen complex features shows that MicroSkill cuts token consumption by over 90%, nearly doubles first-try compilation success rates, eliminates architectural violations entirely, and enables autonomous extraction and registration of seven new skill capsules via a self-learning mechanism. These findings suggest MicroSkill Architecture offers a scalable foundation for building AI-native development systems that are more efficient, more reliable, and capable of evolving over time.

Mohammad Zare, Omid Abdolrahmani

Artificial Intelligence Laboratory at AriooBarzan Engineering Team, Shiraz, Iran

AI Coding Agents Agentic Code Generation Agent Skill Learning LLM Context Management LLM Code Generation

Jun 4, 2026cs.AI

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?

AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools. This creates a new attack surface: an agent can exploit human trust to sabotage development, for instance by inserting malicious code to accomplish a hidden side task. Most prior work studies AI sabotage in AI-only settings, paying limited attention to the role of human oversight in detecting and mitigating such malicious behavior. To address this gap, we conduct the first large-scale study of human oversight in AI coding sabotage. Over 100 participants collaborate with one of four frontier models (Claude-Opus-4.6, GPT-5.4, Gemini-3.1-Pro, and MiniMax-M2.7) on a long-horizon coding task lasting around five hours, designed to mimic real-world workflows. We find that 83/88 (94%) of developers in the no-monitor conditions fail to detect sabotage, and our analysis of participant feedback attributes this vulnerability to minimal code review, plausible cover story, and overtrust in agents. We further test the effectiveness of a safety monitor in one condition: while the monitor reduces sabotage success, sabotage still succeeds in 9/16 (56%) of sessions with a correct monitor alert. Drawing on participant feedback, we offer actionable suggestions for better monitor design. This work complements existing AI safety research and highlights an urgent need for human-centric safety mechanisms that account for human factors, particularly in long-horizon, real-world development settings.

Jingheng Ye, Huiqi Zou, Simon Yu +1

Northeastern University

AI Coding Agents AI Agent Monitoring AI Safety Evaluation Human Oversight of AI

Jun 4, 2026cs.CL

TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework

Repository-level coding benchmarks face a trade-off between task difficulty and evaluation reliability: tasks that challenge frontier models often involve large codebases with incomplete test coverage, while human review does not scale. We introduce TensorBench, a benchmark of 199 feature-addition and refactoring tasks on an open-source compiler-based tensor framework that extends PyTorch with first-class support for dense and sparse tensors. Tasks cover new sparse formats, dense optimization passes, IR transformations, scheduler changes, runtime components, and high-level numerical operators. TensorBench grades each run by applying the agent's patch and running the framework's test suite, which includes the pre-existing randomized regression tests and any tests the agent adds. For feature-addition tasks, a pass means that the patched repository preserves the tested pre-existing behavior and satisfies the agent-added checks for the requested feature. We evaluate seven coding agents spanning three frontier model families and one open-weight model. Pass rates under this criterion range from

64.8\%

for the strongest agent to

22.1\%

for the weakest. Agents pass different subsets of tasks: pairwise Cohen's

κ

ranges from

-0.07

to

0.43

, with

κ= 0.05

for the two strongest agents.

Bobby Yan, Fredrik Kjolstad

Department of Computer Science Stanford University Stanford, CA 94305

AI Coding Agents Benchmark Design Software Engineering Benchmarks AI Agent Benchmarks

Jun 4, 2026cs.SE

ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer

The rapid proliferation of Agent Development Kits (ADKs), SDK-level frameworks for building LLM-powered autonomous agents, has outpaced any empirical understanding of how framework choice affects agent performance. We propose \textbf{LLM-as-a-Developer}, a methodology that replaces human developers with an LLM coding agent that learns each framework's API from documentation, writes agent code, and iteratively repairs it through a validate-and-feedback loop until tests pass. By holding the developer constant and varying only the framework, generation effort becomes a quantitative proxy for API usability and the resulting agents provide a controlled measure of framework effectiveness. We implement this in \textbf{ADK Arena}, a fully automated pipeline with per-framework Docker isolation, a three-level validation pipeline, and benchmark adapters for SWE-bench,

τ^2

-bench, Terminal-Bench, and MCP-Atlas. Evaluating all 51 popular Python ADK frameworks (204 agent--benchmark pairs), we find that: (1)~generation succeeds for 57% of runs, and its cost varies 5.6

\times

across frameworks ($0.6 to $3.4 per agent), a quantitative proxy for API complexity, though cost alone does not predict success; (2)~no single framework dominates: the best single-benchmark ADK agents resolve up to 80% of tasks and can even \emph{beat} general-purpose frontier coding agents at a fraction of the cost, yet the median framework resolves only 32%; (3)~across information-source ablations, genuine framework usage stays within a narrow 28--40% band (highest with raw source access and still 33% with no reference material at all), indicating that documentation, source code, and parametric knowledge are largely substitutable rather than any one being a hard bottleneck.

Jintao Huang, Xiaomin Li, Gaurav Mittal +1

The Ohio State University · Microsoft

AI Coding Agents LLM Agent Evaluation AI Agent Benchmarks

Jun 4, 2026cs.AI

SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization

Recent advances in agentic visualization have enabled the translation of natural language into executable scientific visualization (SciVis) workflows. While general-purpose coding agents show strong capabilities, they often lack the tool-specific expertise required for SciVis tasks. In this work, we present SciVisAgentSkills, a collection of reusable agent skills that augment coding agents for scientific data analysis and visualization by encoding environment assumptions, tool usage patterns, and domain heuristics across scientific tools such as ParaView, napari, VMD, and TTK. We evaluate these skills on Codex and Claude Code using SciVisAgentBench, a benchmark of 108 expert-designed multi-step tasks. Results show that agent skills improve mean task scores across the evaluated suites, with token-efficiency benefits that depend on the agent harness and tool setting. These findings highlight the importance of structured procedural knowledge for enabling reliable, long-horizon SciVis workflows, while also showing that skills should be studied alongside the execution harness that loads and applies them. The skills are available at https://github.com/KuangshiAi/SciVisAgentSkills.

Kuangshi Ai, Haichao Miao, Kaiyuan Tang +2

Univ. Notre Dame · LLNL

Scientific Visualization Data Visualization AI Coding Agents LLM Agent Skill Learning AI Agent Benchmarks Long-Horizon Agent Tasks

Jun 3, 2026cs.SE

Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents

Autonomous software agents hold promise to increase developer productivity but make mistakes and exhibit novel failure modes, making human oversight central to successful human-agent collaboration. Existing research on agent oversight is largely conceptual; normative frameworks exist, but how users actually oversee agents is less known. In this paper, we bridge this gap by providing early empirical anchors for the theoretical discourse on agent oversight. Drawing on interviews with 17 experienced developers, we conduct an exploratory inquiry examining what forms of emergent oversight work developers perform, when, and how. We also document the oversight challenges developers face and the strategies they have started using to address them. We found at least four forms of emergent oversight work: a priori control, co-planning, real-time monitoring, and post hoc review. We show that oversight work is not only reactive and retrospective, as portrayed in existing research, but also preventative and proactive. We describe situated oversight challenges (e.g., difficulty reviewing agent-generated code) and outline heuristics developers adopt to address such challenges (e.g., using test results as guarantees for code correctness). We conclude with high-level takeaways, future research directions, implications for the human-centered design of software agents and for software engineering practice, and limitations of our research.

Shipi Dhanorkar, Samir Passi, Mihaela Vorvoreanu

Microsoft, Redmond, USA

Software Engineering Agents AI Coding Agents Human Oversight of AI Human-AI Collaboration

Jun 3, 2026cs.SE

From Prompt to Process: a Process Taxonomy and Comparative Assessment of Frameworks Supporting AI Software Development Agents

AI tools for programming are no longer just autocomplete or chat assistants: they organize themselves as development frameworks, with process, roles, artifacts and verification. Recent surveys map agents and LLMs for software engineering, but a study centered on the operational frameworks that turn these capabilities into process is missing. We ran a directed search of primary sources, with a functional inclusion criterion and traction measurement, and selected six frameworks: GitHub Spec Kit, OpenSpec, BMAD Method, Get Shit Done (GSD), Spec Kitty and Reversa. Each attacks AI development through a different path: spec-driven development in full and lightweight variants, agent-driven agile planning, context engineering over the agent, worktree isolation and review, and recovery of operational specifications from legacy systems. Our central contribution is a six-dimension process taxonomy: specification, context, roles, execution, validation and portability, with a scoring rubric that turns it into a replicable instrument. We apply it to the six frameworks and an out-of-sample case, Spec-Flow. Two results stand out. Among frameworks that already adopt some process there is convergence: the isolated prompt loses centrality, and persistent artifacts, work contracts, traceability and human review become mechanisms that reduce ambiguity and coordinate agents. And no framework strongly covers all six dimensions, exposing a structural trade-off between process depth and portability across agents. We also found recurring risks: drift between specification and code, excessive trust in generated artifacts, fragility of community extensions, platform dependence and a lack of benchmarks for the complete process. We close with a research agenda for empirical evaluation, focused on intermediate-quality metrics, context governance, installation security and reproducibility.

Sanderson Oliveira de Macedo

Federal Institute of Goias

Software Engineering Agents AI Coding Agents Agentic Workflows AI-Assisted Software Development

Jun 2, 2026cs.AI

Can Generalist Agents Automate Data Curation?

Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data policies against noisy benchmark feedback. We ask whether generalist coding agents can automate this data-curation loop. We introduce Curation-Bench, an agent-centric benchmark that fixes the model, training recipe, and evaluation suite while giving agents command-line access to inspect data, implement policies, submit them to a fixed training/evaluation pipeline, and revise. In a vision-language instruction-tuning instantiation, out-of-the-box agents reach strong published data-selection baselines within ten iterations. However, trajectory analysis reveals a persistent execution-research gap: agents mainly tune local policy variants rather than explore new policy families, even when given strategy guides and paper references. Scaffolds requiring each iteration to cite, instantiate, and adapt a prior method shift agents toward method-guided exploration. The scaffolded agent autonomously composes -- without human design input -- a data-selection policy that outperforms strong published baselines at one-tenth their data budget. Overall, current agents can run the curation loop, but reliable data research requires scaffolded method adaptation, not open-ended prompting alone. Code and benchmark are open-sourced.

Feiyang Kang, Hanze Li, Adam Nguyen +5

1Virginia Tech · University of Illinois Urbana-Champaign · University of Wisconsin-Madison +1

AI Coding Agents Training Data Curation Data Selection Training Data Selection Agent Benchmarks

Jun 2, 2026cs.SE

The Impact of Configuring Agentic AI Coding Tools on Build-vs-Buy Decisions: A Study Protocol

Agentic AI coding tools write code with increasing autonomy and in doing so decide when to import a library and when to implement functionality from scratch. These decisions, whether to build functionality from scratch or buy into an external library, hereafter build-versus-buy, carry direct consequences for software security, licensing compliance, performance, and long-term maintainability. Yet no controlled experimental study has examined what governs build-versus-buy decisions in agentic AI coding tools. Configuration mechanisms, i.e., the means by which developers tailor agentic AI coding tool behavior to a project or workflow, are one of the primary means by which practitioners can influence these decisions. However, it is unclear which configuration mechanisms influence build-versus-buy decisions most effectively. We present a pre-registered protocol to study how configuration mechanisms alter build-versus-buy behavior in two popular agentic AI coding tools: Claude Code and OpenAI Codex. We will execute controlled programming tasks drawn from a benchmark of staged projects, each constructed around identifiable build-versus-buy points, and will manipulate the configuration supplied to each tool, ranging from no configuration, through context files with soft preferences and explicit prohibitions, to Skills (instructions that can be autonomously discovered), MCP-enabled library discovery tools, and permission controls, measuring which libraries the tool selects, whether it discloses newly introduced libraries, and whether those disclosures are complete and accurate. Nine pre-registered hypotheses structure the protocol. The resulting benchmark dataset and analysis pipeline will be released as a reusable artifact for evaluating build-versus-buy behavior in agentic AI coding tools.

Jai Lal Lulla, Matthias Galster, Jie M. Zhang +2

Singapore Management University, Singapore · University of Bamberg, Germany · King’s College London, United Kingdom +1

Software Engineering AI Coding Agents AI Agent Benchmarks

Jun 2, 2026cs.CL

RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions

Agent benchmarks should reflect what users actually ask deployed agents to do, yet existing benchmarks often miss key realism properties of real developer-agent sessions. We introduce RealClawBench, a live benchmark framework built from real OpenClaw sessions to capture the distribution, diversity, and real-world difficulty of deployed agent use. Real user requests are challenging to benchmark because they often depend on local execution environments, involve implicit or underspecified intent, and require nontrivial verification. RealClawBench addresses these challenges with two core mechanisms: reconstructed execution environments and deterministic verifiable scorers, which together convert real sessions into reproducible, automatically scored tasks. The resulting release contains 281 executable tasks sampled from a much larger real-session pool while preserving the source distribution, with maximum final-vs-source Jensen-Shannon divergence of 0.0448. Evaluating 14 contemporary models shows that the best system solves only 65.8% of tasks, revealing substantial headroom on realistic developer-agent workloads. By turning real deployed sessions into controlled evaluation instances, RealClawBench provides a practical path toward benchmarks that better measure agent capability in actual use. Code is available at:https://anonymous.4open.science/r/real-claw-bench-582B.

Zongwei Lv, Zhewen Tan, Yaoming Li +7

1Peking University · 2Qiyuan Tech · 2Qiyuan Tech*

Computer-Use Agent Benchmarks AI Coding Agents Software Engineering Benchmarks AI Agent Benchmarks Automated Evaluation Agent Benchmarks

Jun 2, 2026cs.AI

Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing

AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficiency for non-English text and structural entropy in conversational prompts. Existing approaches act reactively by compressing already-bloated contexts or intervening after failures occur. We introduce a pre-flight, edge-side prompt-rewriting middleware that operates between the developer and the cloud agent. A local Llama 3.2 (3B) model performs cross-lingual translation into English, structural rewriting into a compact task-oriented format, and regex-validated rewrite-with-fallback safeguards to ensure the optimized prompt is never larger than the original. We evaluate on OMH-Polyglot, a multilingual coding benchmark spanning Turkish, Arabic, Chinese, and code-switched specifications. Across three commercial LLM backends, the middleware reduces prompt tokens by 34-47 percent and total tokens by up to 18.8 percent while preserving or improving task accuracy. Ablation studies show that gains arise primarily from the rewriting stage rather than simple function-name extraction. Compared with LLMLingua-2 at matched compression rates, our method consistently achieves superior OckScore performance across all evaluated backends. These results demonstrate that proactive prompt optimization can substantially reduce inference costs without sacrificing coding quality.

Mehmet Utku Colak

Department of Computer Engineering, Istanbul Technical University · Istanbul, Turkey

AI Coding Agents LLM Prompting LLM Inference Acceleration Prompt Compression

Jun 1, 2026cs.MA

Agentic-J: An AI Agent for Biological Microscopy Image Analysis

Biological image analysis increasingly demands integration across heterogeneous tools, programming environments, and domain knowledge that few researchers can command simultaneously. We present Agentic-J, a containerised, multi-agent AI assistant, primarily for ImageJ/Fiji that enables biologists to specify analysis tasks in natural language, from nuclei segmentation and cell tracking to multi-condition quantification. The agent generates executable scripts organised into a documented project structure, so every analysis decision is traceable and the workflow can be reproduced or shared. The specialised sub-agents handle plugin management, code generation, debugging, quality assurance, and statistical reporting. In this paper we introduce the system's design, demonstrate real biological microscopy image analysis workflows, and detailed the technical implementation.

Lukas Johanns, Marilin Moor, Davide Panzeri +9

Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V., Dortmund, Germany. · Institute of Computer Science, University of Tartu, Tartu, Estonia. · Faculty of Computer Science, Ruhr University Bochum, Bochum, Germany. +4

AI Coding Agents Scientific Workflow Automation Microscopy Image Analysis

Jun 1, 2026cs.AI

Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks

We consider LLM-based algorithm development through a case study on contractionorder optimisation for tensor networks with OpenEvolve. We pay particular attention to the choice of the LLM as well as design choices such as evaluation metric and test instances. Our results highlight both the promise of verifier-guided evolutionary coding agents for algorithm development/improvement and the continuing importance of evaluation, validation, and interpretation -- and corresponding challenges -- by the human scientist.

Fabian Hoppe, Melven Röhrig-Zöllner, Philipp Knechtges

German Aerospace Center (DLR), Institute of Software Technology, department High-Performance Computing, Cologne (Germany)

Tensor Networks Automated Algorithm Discovery AI Coding Agents Large Language Model-Guided Optimization